An AI-powered tool to clean manga panels.

Text preprocessing tools in python.

📊 python package for performing deduplication using flexible text matching and cleaning in pandas dataframe

🛡️ AI DeWatermarker — Real-time AI watermark & text obfuscation detector and cleaner. Detects hidden Unicode, invisible characters, and homoglyph attacks — all processed locally in your browser for full privacy.

🖹 Offline Text Cleaner and Formatter

Simple Python package (CLI/Python API) for getting japanese readings (yomigana) and accents using MeCab.

Khodnevis Normalizer: A Python library for Persian text preprocessing.

Corpora and scripts for cleaning political science texts. Scripts are translated into transformations that support SAGE Texti.

Filter and clean profanity and bad words from text, especially for Indian languages.

Persian text cleaner with additional features on Parsivar package.

Utility that automates name anonymizing over batches of text files

Webmaster's desktop productivity tools

A tool for cleaning up text copied out of LLM tools like Claude Code or Coded

This repository is the implementation of "Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context".

Reveal & remove invisible, dangerous & confusable characters in your text — zero-width spaces, BOMs, bidi (Trojan Source), homoglyphs, smart quotes. 100% local. Web app + library + CLI.

Instantly clean text by removing repeated phrases and clutter. Fast, browser-based tool with an optional Firebase-based metrics system.

A simple command-line tool to clean up messy text files and copied text snippets.

Bangla Language Processing Toolkit

A simple web tool to clean and format text instantly.

A clean, client-side utility to convert Word, Google Docs, and OneNote formatting into AI-ready Markdown for Prompt Engineering.